一种基于加权均方误差系数的评价因子筛选方法

An Evaluation Factor Screening Method Based on Weighted Mean Square Error Coefficients

摘要: 评价因子的筛选一直是统计分析中的热门话题，目前对因子筛选方法很多，如综合指数法、全局主成分分析方法等；这些方法在特定的环境中均得到充分的运用，但是当因子间的相关性较强时，这些方法的分析不理想，如在交通助推农村产业的分析中就得不到与实际相符的结果。为了克服此问题，本文提出了一种加权均方误差系数法；并以贵州交通对农村产业的影响为例进行实证分析。实验结果表明，我们的方法是有效。

Abstract: Evaluation factors screening has always been a hot topic in statistical analysis. At present, there are many methods for screening factors, such as the integrated index method, the global principal component analysis method, etc.; these methods are fully used in specific environments, but when the correlation between factors is strong, the analysis of these methods is not ideal. For example, in the analysis of the traffic boosting rural industry, the results are not in line with the actuality. To overcome this problem, a weighted mean square error coefficient method is proposed in this paper; and the impact of transportation on rural industries in Guizhou is used as an example for empirical analysis. The experimental results show that our method is effective.